Alternatives and similar repositories for DiffusionSfM

Users that are interested in DiffusionSfM are comparing it to the libraries listed below

• hwjiang1510 / RayZer

  View on GitHub
  Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"
  ☆408Nov 24, 2025Updated 2 months ago
• Brummi / anycam

  View on GitHub
  Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)
  ☆294May 7, 2025Updated 9 months ago
• CUT3R / CUT3R

  View on GitHub
  Official implementation of Continuous 3D Perception Model with Persistent State
  ☆1,329Aug 27, 2025Updated 5 months ago
• cvg / mpsfm

  View on GitHub
  MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)
  ☆482Jul 9, 2025Updated 7 months ago
• Haian-Jin / LVSM

  View on GitHub
  [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
  ☆494Aug 4, 2025Updated 6 months ago
• SunYangtian / UniGeo

  View on GitHub
  UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
  ☆135Jun 10, 2025Updated 8 months ago
• ant-research / FLARE

  View on GitHub
  ☆700May 1, 2025Updated 9 months ago
• Inception3D / Easi3R

  View on GitHub
  [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.
  ☆514Apr 1, 2025Updated 10 months ago
• TencentARC / GeometryCrafter

  View on GitHub
  [ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
  ☆428Oct 2, 2025Updated 4 months ago
• jzr99 / Geo4D

  View on GitHub
  [ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
  ☆410Jun 6, 2025Updated 8 months ago
• ComputationalRobotics / XM-code

  View on GitHub
  Code for our paper "Building Rome with Convex Optimization".
  ☆173Updated this week
• yyfz / Pi3

  View on GitHub
  [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning
  ☆1,630Jan 28, 2026Updated 2 weeks ago
• mega-sam / mega-sam

  View on GitHub
  Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
  ☆1,225Jan 5, 2026Updated last month
• NVlabs / GaussianSTORM

  View on GitHub
  [ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes
  ☆331May 22, 2025Updated 8 months ago
• pals-ttic / fastmap

  View on GitHub
  A fast and simple structure from motion pipeline written in Pytorch.
  ☆246Aug 22, 2025Updated 5 months ago
• G-1nOnly / Dens3R

  View on GitHub
  [ICLR2026] Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"
  ☆365Sep 29, 2025Updated 4 months ago
• Junyi42 / monst3r

  View on GitHub
  Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
  ☆1,334Jun 16, 2025Updated 7 months ago
• brianwang00001 / sparse-vggt

  View on GitHub
  Code for Faster VGGT with Block-Sparse Global Attention
  ☆90Nov 14, 2025Updated 3 months ago
• YkiWu / Point3R

  View on GitHub
  [NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
  ☆180Sep 26, 2025Updated 4 months ago
• facebookresearch / fast3r

  View on GitHub
  [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
  ☆1,501May 7, 2025Updated 9 months ago
• apple / ml-matrix3d

  View on GitHub
  [CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One
  ☆585Jul 15, 2025Updated 6 months ago
• jiah-cloud / Align3R

  View on GitHub
  [CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
  ☆454Apr 4, 2025Updated 10 months ago
• facebookresearch / mvdust3r

  View on GitHub
  Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page …
  ☆579Updated this week
• liruilong940607 / prope

  View on GitHub
  Cameras as Relative Positional Encoding
  ☆671Dec 18, 2025Updated last month
• VITA-Group / E3D-Bench

  View on GitHub
  Official implementation of "E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models"
  ☆104Jun 4, 2025Updated 8 months ago
• Stereo4d / stereo4d-code

  View on GitHub
  Stereo4D dataset and processing code
  ☆290Nov 4, 2025Updated 3 months ago
• hwjiang1510 / MegaSynth

  View on GitHub
  Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025)
  ☆199May 20, 2025Updated 8 months ago
• ruili3 / awesome-dust3r

  View on GitHub
  🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.
  ☆787Nov 5, 2025Updated 3 months ago
• cvg / NoPoSplat

  View on GitHub
  [ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
  ☆929Sep 2, 2025Updated 5 months ago
• ga1i13o / mcloc_poseref

  View on GitHub
  Official repository of the CVPR24 paper "The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement"
  ☆58Aug 10, 2024Updated last year
• MarkYu98 / madpose

  View on GitHub
  [CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affin…
  ☆231Apr 8, 2025Updated 10 months ago
• cvg / depthsplat

  View on GitHub
  [CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth
  ☆1,146Apr 27, 2025Updated 9 months ago
• btsmart / splatt3r

  View on GitHub
  Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
  ☆774Nov 23, 2024Updated last year
• HengyiWang / spann3r

  View on GitHub
  [3DV'25] 3D Reconstruction with Spatial Memory
  ☆1,116Feb 25, 2025Updated 11 months ago
• nianticlabs / acezero

  View on GitHub
  [ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning…
  ☆806Nov 10, 2025Updated 3 months ago
• ComputationalRobotics / PreF3R

  View on GitHub
  ☆66Nov 27, 2024Updated last year
• RongLiu-Leo / beta-splatting

  View on GitHub
  [SIGGRAPH'25] Official implementation for the paper "Deformable Beta Splatting"
  ☆288Jan 27, 2026Updated 2 weeks ago
• hujiecpp / PE3R

  View on GitHub
  PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start explorin…
  ☆395Apr 1, 2025Updated 10 months ago
• facebookresearch / vggsfm

  View on GitHub
  VGGSfM: Visual Geometry Grounded Deep Structure From Motion
  ☆1,360Mar 11, 2025Updated 11 months ago